Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rouge
    -0.07
    FromArray
    -0.07
     lineNumber
    -0.07
    [vi
    -0.07
    (actor
    -0.07
    ropping
    -0.06
     shifts
    -0.06
     decrement
    -0.06
    대로
    -0.06
    (MenuItem
    -0.06
    POSITIVE LOGITS
     OO
    0.06
     ASA
    0.06
     českých
    0.06
     simpler
    0.06
     İstanbul
    0.06
    ön
    0.06
     Flag
    0.06
     CPPUNIT
    0.05
    している
    0.05
     vegas
    0.05
    Act Density 0.024%

    No Known Activations